The Fault Tolerant Parallel Algorithm: the Parallel Recomputing Based Failure Recovery

Yang, Xuejun; Du, Yunfei; Wang, Panfeng; Fu, Hongyi; Jia, Jia; Wang, Zhiyuan; Suo, Guang

doi:10.1109/pact.2007.4336212

Cited by 17 publications

(13 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As already explained, reliability speedup, energy productivity speedup and parallel software development productivity speedup are three kinds of speedups generated by (8) in terms of different sets, e.g. S R = P · U C · U R , S E = P · U C · U E and S D = P · U C · U D .…”

Section: Definitionmentioning

confidence: 99%

“…We propose the synthetic system productivity speedup metric in formula (8). The productivity variables of large-scale parallel computer systems are indeed not limited to the above four productivity variables.…”

Section: Definitionmentioning

confidence: 99%

“…With the parallel computing systems scaling-up, the systems will not only correspondingly meet the traditional requirement of computing performance [2][3][4][5], but also address the ongoing technical challenges in the current large-scale parallel computing domain regarding reliability, energy consumption, parallel software development, etc. [6][7][8][9][10][11].…”

mentioning

confidence: 99%

“…Therefore, fault tolerance techniques should be introduced into largescale parallel computer systems to achieve high reliability [8,14,15].…”

mentioning

confidence: 99%

See 3 more Smart Citations

An effective speedup metric for measuring productivity in large-scale parallel computer systems

Yang

Wang

2009

J Supercomput

Self Cite

View full text Add to dashboard Cite

With the parallel computer systems scaling-up, the measure index for performance of the systems demands a shift from traditional "high performance" to "high productivity." This brings a new challenge to defining a synthetic, yet meaningful, measure index of multiple productivity variables; namely computing performance, reliability, energy consumption, parallel software development, etc. Traditional measures for large-scale parallel computer systems merely focus on computing performance, and are incapable of measuring the multiple productivity variables simultaneously in an effective manner. A recently proposed market-related money model, which pursues high utility/cost ratio, relies on money as a measure to consider the multiple productivity variables. Differing from the previous models, this paper proposes a novel system productivity speedup metric for large-scale parallel computer systems. The metric uses speedup instead of money to comprehensively unify the measures of multiple productivity variables. Finally, we propose a trade-off productivity measurement to weigh different productivity variables, to address different design targets. The measurement can facilitate the system evaluation, expose future technique tendencies, and guide future system design.

show abstract

Section: Definitionmentioning

confidence: 99%

Section: Definitionmentioning

confidence: 99%

mentioning

confidence: 99%

“…Therefore, fault tolerance techniques should be introduced into largescale parallel computer systems to achieve high reliability [8,14,15].…”

mentioning

confidence: 99%

See 2 more Smart Citations

An effective speedup metric for measuring productivity in large-scale parallel computer systems

Yang

Wang

2009

J Supercomput

Self Cite

View full text Add to dashboard Cite

show abstract

“…Currently, the Checkpoint/Restart technique [1] has been widely used in large scale parallel computing. This mechanism saves the state of the computation to stable storage (disk) periodically.…”

Section: Introductionmentioning

confidence: 99%

MMPI: A Scalable Fault Tolerance Mechanism for MPI Large Scale Parallel Computing

Wang

Yang

Zhou

2010

2010 10th IEEE International Conference on Computer and Information Technology

Self Cite

View full text Add to dashboard Cite

At present, Checkpoint/Restart is one of the most popular fault tolerance mechanisms for large scale parallel computing. However, the time to save a global checkpoint reaches and even exceeds the mean-time-between-failures (MTBF) of the component when the performance of the system is between Peta(10 15 ) and Exa(10 18 ) flops, which limits the scalability of the parallel computing. In this paper, a scalable fault tolerance mechanism is designed for MPI-oriented large scale parallel computing, which not only can deal with the failstop faults concerned by Checkpoint/Restart, but also can deal with most data errors that are not perceived by hardware. Firstly, we define the concept of redundant-process cluster (RPC), design running techniques that support MMPI, and study the implementation of MMPI. Secondly, we present the models of fault tolerance parallel speedup, Lastly, we verify the validity and scalability of MMPI fault tolerance mechanism.

show abstract

Fault Recovery Based on Parallel Recomputing in Transactional Memory System

Song

Jia

2011

Electrical Engineering and Control

View full text Add to dashboard Cite

The Fault Tolerant Parallel Algorithm: the Parallel Recomputing Based Failure Recovery

Cited by 17 publications

References 12 publications

An effective speedup metric for measuring productivity in large-scale parallel computer systems

An effective speedup metric for measuring productivity in large-scale parallel computer systems

MMPI: A Scalable Fault Tolerance Mechanism for MPI Large Scale Parallel Computing

Fault Recovery Based on Parallel Recomputing in Transactional Memory System

Contact Info

Product

Resources

About